OpenAI baseUrl support #216
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
🤖 Generated with opencode Co-Authored-By: opencode <noreply@opencode.ai>
🤖 Generated with opencode Co-Authored-By: opencode <noreply@opencode.ai>
Introduces a new global configuration option `alwaysAllowPermissions` and a corresponding CLI flag `--always-allow-permissions` (shorthand `-A`). When this setting is enabled, all permission prompts during a session are bypassed, and operations are automatically allowed. This provides a more streamlined experience for users who trust all operations performed by the tool. The configuration is persisted across sessions. 🤖 Generated with opencode Co-Authored-By: opencode <noreply@opencode.ai>
The --always-allow-permissions flag no longer automatically updates the user's configuration file. This change ensures that the setting is manually configured by the user, and only affects the current session unless explicitly set in the config.
This commit introduces the ability for users to hide and show the sidebar by pressing `ctrl+b`. This feature provides more screen real estate for the main chat view, which is especially useful on smaller screens. The implementation involves: - Adding a `hidden` state to the `sidebarCmp` component. - Creating a `ToggleSidebarMsg` to toggle the sidebar's visibility. - Adding a keybinding (`ctrl+b`) to the chat page to dispatch the message. - Modifying the `splitPaneLayout` to forward the message to the sidebar. 🤖 Generated with opencode Co-Authored-By: opencode <noreply@opencode.ai>
When the sidebar is hidden, the chat view now expands to fill the available space. This is achieved by updating the layout to recalculate its dimensions when the sidebar's visibility changes. This also fixes a bug where the status bar would overlap the chat input when the sidebar was hidden.
…feat/update-gemini-flash-model'
This commit introduces a confirmation step for canceling an ongoing agent operation. Users must now press the `esc` key twice in quick succession to cancel, preventing accidental cancellations. The implementation involves: - Adding a timeout to the `esc` key press in the chat page. - Passing the `firstEsc` state down to the message list component to update the help message. - Adding a `Model()` method to the `layout.Container` to allow the chat page to access the message list's model. 🤖 Generated with opencode Co-Authored-By: opencode <noreply@opencode.ai>
pulling in double esc pr
|
|
|
my provider is not openai compatible |
|
looking forward to merging this feature, happy to use it. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hi, awesome project! I had some trouble getting OpenAI API compat endpoints working, so I made some minimal changes to make it easier. This adds basic OpenAI-compatible provider support as a practical stopgap solution while you guys are discussing other methods. LiteLLM is the easy button and a great opensource project, fwiw!
Adds environment variable support for:
This allows users to immediately use any OpenAI API compatible endpoint like LocalAI.io without code changes.
Sorry if I mangled any Go, first time for everything.
Thanks for your efforts, much appreciated!